[Fwd: Feedback about the content processing framework]

Moez Mahfoudh wrote:

> >
> > Currently: The last chunk has len==0, buf==NULL. The flag is defined, but not used all over yet.
> > store a state variable for headers seen, and test for EOF/LASTCHUNK by buf==NULL || flags & FILTER_EOF. That'll cover both bases
> > until I've finished the tidyup.
>
> Sorry for insisting, but in my tests, I cannot see such a behavior. There is no call for my filter function with buf=NULL or len=0.
>
> If you want to try it, here is its code:
>
> static void clientFilterDummy(char *buf,size_t len,dlink_list *filter_list,FILTER_list *filters,unsigned int flags,void *data)
> {
> FILTER_list *temp_filter=filters->node.next->data;
>
> debug(1,1)("**** Spying my dummy filter (buf=%x,len=%d,flags=%d\n",buf,len,flags);
> temp_filter->filter(buf,len,filter_list,temp_filter,temp_filter->data);
> }
>
> >
> > Regarding the request/reply question, I've just checked and there is no way for you to take my suggestion :-/
> >
> > I'll update the API for the makestate function and email the list when I've done that.
> >
> > The reason I don't want to alter the filter API is because the filters are currently generic (as I mentioned :-])
>
> OK, I understand that.
>
> Thank you...
>
> --Moez
Received on Wed Jan 31 2001 - 03:06:25 MST